Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    negations and expressions of doubt or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erable
    -0.15
    itmap
    -0.15
    åĽ²
    -0.15
    ottage
    -0.15
    gebung
    -0.15
    ENTA
    -0.14
    orges
    -0.14
    (strpos
    -0.14
    ikh
    -0.14
    åĽ´
    -0.14
    POSITIVE LOGITS
    827
    0.18
    antino
    0.17
    MF
    0.17
    H
    0.15
    uder
    0.15
    ant
    0.15
    t
    0.15
     nor
    0.15
    770
    0.14
    ICE
    0.14
    Act Density 0.032%

    No Known Activations